LyricSIM: A novel Dataset and Benchmark for Similarity Detection in Spanish Song LyricS
This provides a new benchmark for similarity detection in Spanish lyrics, which is incremental as it adapts existing methods to a specific domain and language.
The authors tackled the problem of semantic similarity detection in Spanish song lyrics by creating a new dataset of 676 high-quality annotated pairs from an initial 2775, and established baseline results using state-of-the-art language models.
In this paper, we present a new dataset and benchmark tailored to the task of semantic similarity in song lyrics. Our dataset, originally consisting of 2775 pairs of Spanish songs, was annotated in a collective annotation experiment by 63 native annotators. After collecting and refining the data to ensure a high degree of consensus and data integrity, we obtained 676 high-quality annotated pairs that were used to evaluate the performance of various state-of-the-art monolingual and multilingual language models. Consequently, we established baseline results that we hope will be useful to the community in all future academic and industrial applications conducted in this context.